feat: FRIDAY Voice stack on the GPU machine; VoiceCoach history

FRIDAY Voice (speaches GPU STT/TTS + hermes agent + push-to-talk console) on
.150 Docker Desktop, fronted by coach.hobbs.farm. Also captures the VoiceCoach
compose/agent trees and deploy notes it replaced, which had never been committed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

compose/hf-pdocker-01/voicecoach/speechbrain-service/Dockerfile

@@ -0,0 +1,33 @@
+FROM python:3.11-slim
+
+RUN apt-get update && apt-get install -y \
+    libsndfile1 \
+    ffmpeg \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Pre-download the SpeechBrain model at build time
+RUN python -c "\
+from speechbrain.inference.interfaces import foreign_class; \
+foreign_class( \
+    source='speechbrain/emotion-recognition-wav2vec2-IEMOCAP', \
+    pymodule_file='custom_interface.py', \
+    classname='CustomEncoderWav2vec2Classifier', \
+    savedir='/app/models', \
+    run_opts={'device': 'cpu'}, \
+); \
+print('Model downloaded successfully.')"
+
+COPY . .
+
+EXPOSE 8001
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=90s \
+    CMD python -c "import httpx; httpx.get('http://localhost:8001/health').raise_for_status()"
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8001", "--workers", "1"]